TriAttention: Efficient Long Reasoning with Trigonometric KV Compression | Dark Hacker News

Dark Hacker News

new|best|ask|show|jobs

Built with the HackerNews API. Developed by LJT.AI

Note: The HackerNews API provides up to 500 stories per category

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression(weianmao.github.io)

2 points by tamnd 41 days ago | 0 comments

No comments yet

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression | Dark Hacker News